CN111159318A - Method, apparatus, device and medium for aggregating points of interest - Google Patents
Method, apparatus, device and medium for aggregating points of interest Download PDFInfo
- Publication number
- CN111159318A CN111159318A CN201811324278.9A CN201811324278A CN111159318A CN 111159318 A CN111159318 A CN 111159318A CN 201811324278 A CN201811324278 A CN 201811324278A CN 111159318 A CN111159318 A CN 111159318A
- Authority
- CN
- China
- Prior art keywords
- interest
- points
- input
- interest points
- candidate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A method, apparatus, device and medium for aggregating points of interest, comprising: acquiring related interest points of the input interest points as candidate interest points based on the attributes of the input interest points; screening the candidate interest points according to a preset rule, and confirming the interest points which cannot be judged whether the candidate interest points can be aggregated with the input interest points as suspected interest points; inputting the suspected interest point into a pre-trained machine learning model to obtain the similarity between the suspected interest point and the input interest point; and if the similarity is greater than a preset threshold value, determining the corresponding suspected interest point as an interest point capable of being aggregated with the input interest point. After the embodiment of the invention is adopted, whether the interest point to be processed currently exists in the database can be distinguished.
Description
Technical Field
The present invention relates to the field of map data processing, and in particular, to a method, an apparatus, a device, and a computer storage medium for aggregating points of interest.
Background
A Point of Interest (POI) belongs to map basic data, and includes attributes such as name, category, coordinate, and address. When the interest point to be processed is acquired, whether the current interest point to be processed exists in a database of map data needs to be judged, and if the current interest point to be processed exists in the database, the interest point needs to be aggregated with the existing interest point in the database; if the current interest point to be processed does not exist in the database, the interest point needs to be stored in the database.
During the production of the point of interest data, it is found that: two or more interest points to be processed, which belong to the same interest point, may have differences in the description of some attributes; and two or more points of interest, which are classified as different points of interest, are the same in the description of certain attributes. Based on the above situation, there is a technical problem that it is difficult to determine whether the currently pending interest point already exists in the database.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a computer storage medium for aggregating interest points, which can distinguish whether the current interest points to be processed exist in a database.
A method of aggregating points of interest, comprising:
acquiring interest points related to input interest points as candidate interest points based on the attributes of the input interest points;
screening the candidate interest points according to a preset rule, and confirming the interest points which cannot be judged whether the candidate interest points can be aggregated with the input interest points as suspected interest points;
inputting the suspected interest point into a pre-trained machine learning model to obtain the similarity between the suspected interest point and the input interest point;
and if the similarity is greater than a preset threshold value, determining the corresponding suspected interest point as an interest point capable of being aggregated with the input interest point.
The obtaining of the interest points related to the input interest points as candidate interest points based on the attributes of the input interest points comprises: and determining a candidate region based on the coordinates of the input interest points, and taking the interest points in the candidate region as candidate interest points.
The obtaining of the interest points related to the input interest points as candidate interest points based on the attributes of the input interest points comprises:
based on one attribute of the input interest point, taking the interest point related to the input interest point as an initial selection interest point; and eliminating interest points different from the input interest points from the primarily selected interest points by adopting other attributes of the input interest points to obtain the candidate interest points.
The one attribute comprises a coordinate; the other attributes include one or more of a name, a category, and an address.
Before the inputting the suspected interest point into a pre-trained machine learning model and obtaining the similarity between the suspected interest point and the input interest point, the method further includes:
the machine learning model is trained by a set of positive samples including polymerizable points of interest and a set of negative samples including non-polymerizable points of interest.
An apparatus for aggregating points of interest, comprising:
the candidate module is used for acquiring interest points related to the input interest points as candidate interest points based on the attributes of the input interest points;
the judging module is used for screening the candidate interest points according to a preset rule and confirming the interest points which can not be judged whether to be aggregated with the input interest points as suspected interest points;
a similarity module, configured to input the suspected interest point into a pre-trained machine learning model to obtain a similarity between the suspected interest point and the input interest point
And the aggregation module is used for determining the corresponding suspected interest point as an interest point which can be aggregated with the input interest point if the similarity is greater than a preset threshold value.
The candidate module is specifically configured to determine a candidate region based on the coordinates of the input interest point, and use an interest point in the candidate region as a candidate interest point.
The candidate module is specifically configured to use an interest point related to the input interest point as an initially selected interest point based on one attribute of the input interest point;
and eliminating interest points with different differences from the input interest points from the primarily selected interest points by adopting other attributes of the input interest points to obtain the candidate interest points.
The one attribute comprises a coordinate;
the other attributes include one or more of a name, a category, and an address.
The apparatus further comprises a training module;
the training module is configured to train the machine learning model through a positive sample set and a negative sample set, where the positive sample set includes polymerizable interest points and the negative sample set includes non-polymerizable interest points.
An apparatus for aggregating points of interest,
a memory for storing a program;
a processor for executing the program stored in the memory to perform the method of aggregating points of interest as described above.
A computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement a method as described above.
According to the technical scheme, the related POI of the input POI is obtained as the candidate POI based on the attribute of the input POI; firstly, confirming POIs which cannot be judged whether the POIs can be aggregated with input POIs as suspected POIs in the candidate POIs according to a preset rule; then, using a pre-trained machine learning model, POIs that can be aggregated with the input POI are determined among the suspected POIs. The method has the advantages that the preset rules are combined with the pre-trained machine learning model, the POI aggregated with the input POI is determined in the suspected POI, whether the POI with different attributes is the same POI or not can be determined, and whether the POI to be processed currently exists in the database or not can be distinguished, and the processing method is high in efficiency.
Drawings
The present invention will be better understood from the following description of specific embodiments thereof taken in conjunction with the accompanying drawings, in which like or similar reference characters designate like or similar features.
FIG. 1 is a flowchart illustrating a method for aggregating points of interest according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the positions of four POIs in accordance with an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of an apparatus for aggregating POIs according to an embodiment of the present invention;
fig. 4 is a block diagram of an exemplary hardware architecture of a computing device of the method and apparatus for aggregating points of interest of embodiments of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings and specific embodiments.
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
In the geographic information system, one POI may be one house, one shop, one bus station, and the like. The POI may include a variety of attributes, such as: name, category, coordinates, and address, etc. Wherein the name is the name of the POI, such as: beijing west station. The category is the category to which the POI belongs, such as: catering, lodging, traveling and the like. The coordinates may be geographic location coordinates such as longitude, latitude; the coordinates may also be relative coordinates, such as: a position 1000 meters from beijing west station. The address is a collection of information where POIs can be found.
Fig. 1 is a schematic flow chart of a method for aggregating interest points according to an embodiment of the present invention, which specifically includes:
s101, acquiring POI related to the input POI as candidate POI based on the attribute of the input POI.
There are various attributes of POIs, and POIs related to an input POI may be determined as candidate POIs according to the attributes of the POIs. Specifically, there may be a plurality of methods for recalling candidate POIs from the database according to the attribute of the input POI.
In an embodiment of the present invention, in consideration of the fact that the probability that a plurality of POIs are the same POI is relatively high in the case of the same or similar coordinates, a candidate area may be determined based on the coordinates of the input POI, and POIs within the range of the candidate area may be recalled as candidate POIs. The size of the candidate area range can be comprehensively determined according to the number and the precision of the candidate POI needing to be recalled. The larger the range setting of the candidate area is, the larger the number of recalled candidate POIs is, and the lower the precision is; the smaller the candidate area is set, the smaller the number of recalled candidate POIs is, and the accuracy is relatively high.
Referring to fig. 2, fig. 2 is a schematic position diagram of POI _ A, POI _ B, POI _ C and POI _ D according to an embodiment of the present invention. This is explained below by taking POI _ a as the POI to be processed, i.e., the input POI as an example: first, based on the coordinates of POI _ a, candidate regions are determined, such as: determining a candidate area by taking the coordinate of the POI _ A as a circle center and a preset length as a radius; in this candidate area, the recalled POIs, i.e., POI _ B and POI _ C in this example, are candidate POIs of POI _ a.
In another embodiment of the present invention, considering that there are multiple attributes of the POI, the POI related to the input POI may be further used as the initial POI based on one attribute of the input POI; and then, other types of attributes of the input POI are adopted, POI different from the input POI are excluded from the initial selection POI, and candidate POI are obtained. Because the coordinate has a large influence on whether the POIs are the same or not, and whether the coordinates are the same or not is easy to judge, preferably, one attribute may be the coordinate; other attributes may include one or more of a name, a category, and an address.
Those skilled in the art will appreciate that, based first on the attributes of the input POI: name, using the POI related to the input POI as the initial selection POI; further, it is also possible to obtain a candidate POI by excluding a POI different from the input POI from the initial POI selection by using one or more of the coordinates, category, and address of the input POI.
Meanwhile, since the attributes of the POI include, but are not limited to, name, category, coordinate, and address, other attributes of the POI are also applicable, as long as the purpose of recalling the candidate POI is achieved.
S102, screening the candidate POI according to a preset rule, and confirming the POI which cannot be judged whether the input POI can be aggregated as a suspected POI.
The preset rule may relate to one or more attributes of the POIs, which is a judgment basis for identifying the difference between the two POIs.
As an example, the preset rule may be whether or not the building numbers in the addresses of the two POIs are the same. Such as: when the attribute addresses of the input POI and the candidate POI both contain building numbers, if the numbers of the building numbers of the two POIs are greatly different, the two POIs can be determined to be different POIs, the candidate POI can be deleted, subsequent judgment programs do not need to be executed, and the efficiency is improved. Similarly, when the candidate POI and the input POI are enough judged to be polymerizable POIs through the preset rule, the polymerization operation is directly carried out, and a subsequent judgment program is not required to be executed, so that the efficiency is improved.
The preset rule may further include: one or more sub-rules. If the candidate POI accords with all the sub-rules, judging that the candidate POI is the same POI as the input POI; and if the candidate POI does not accord with any sub-rule, judging that the candidate POI is a different POI from the input POI.
Due to the diversity and complexity of POI, the difference and the sameness between POI are difficult to distinguish only by the preset rule in many times; and when the candidate POI and the input POI can not be judged to be polymerizable according to the preset rule, taking the candidate POI as a suspected POI.
S103, inputting the suspected POI into a pre-trained machine learning model to obtain the similarity between the suspected POI and the input POI.
The machine learning model may be a two-class machine learning model, such as: random forests, logistic regression, GBDT, etc.; the two-classification machine learning model required to be used can be obtained through training of the positive sample set and the negative sample set.
During training, the positive sample set includes a set of POIs that are aggregatable, although some attributes differ in their description; the negative sample set includes a set of POIs that belong to a non-aggregate set, although some attributes may be identical in description.
As an example: the positive sample set may include POI _1 and POI _2, and the negative sample set may include POI _3 and POI _ 4.
POI _ 1: coordinates are as follows: north latitude N39 ° 53 '35.95 ", east longitude E116 ° 19' 0.49". Name: beijing train west station. The category: and (5) going out. Address: dongluo No. 118 of Lotus flower pool in Fengtai district, Beijing.
POI _ 2: coordinates are as follows: north latitude N39 ° 53 '35.95 ", east longitude E116 ° 19' 0.49". Name: beijing west station. The category: and (5) going out. Address: dongdui No. 100 lotus pool in Toutai district, Beijing.
POI _ 3: coordinates are as follows: north latitude N39 ° 00 '00 ", east longitude E116 ° 00' 00". Name: beijing West. The category: and (5) going out. Address: dongluo No. 1 lotus flower pool in Fengtai district, Beijing.
POI _ 4: coordinates are as follows: north latitude N38 ° 00 '00 ", east longitude E115 ° 00' 00". Name: a Beijing hotel. The category: and (4) lodging. Address: tou 100 Hai lake district school of Beijing.
And predicting the similarity of each suspected POI and the input POI by using the machine learning model obtained by training. The similarity is a parameter output after comprehensively measuring the similarity between the suspected POI and the attributes of the input POI. In the machine learning model, the weight of each attribute may be preset, and the similarity between the suspected POI and the input POI is finally output. The similarity is higher, the similarity between the suspected POI and the input POI is higher; correspondingly, the smaller the similarity, the lower the similarity between the suspected POI and the input POI is.
And S104, if the similarity is larger than a preset threshold value, confirming the corresponding suspected POI as a POI capable of being aggregated with the input POI.
In an embodiment of the present invention, a second preset threshold may be further set, and if the similarity is smaller than the second preset threshold, the corresponding suspected POI is determined as a POI that cannot be aggregated with the input POI; if the similarity is less than or equal to a preset threshold and greater than or equal to a second preset threshold, the suspected POI is still determined as a suspected POI, and the further determination is carried out by adopting other modes. Those skilled in the art will understand that the values of the preset threshold and the second preset threshold may be flexibly set according to the actual usage scenario.
In an embodiment of the present invention, candidate POIs are recalled from a database based on attributes of the input POIs; and preliminarily screening the candidate POI by using a preset rule to obtain a suspected POI, namely: screening out POIs which are obviously the same as or different from the input POI from the candidate POIs; and further predicting the similarity between the suspected POI and the input POI by utilizing a machine learning model, and further confirming whether the input POI and the candidate POI can be polymerized according to the similarity. The method combines the preset rules with the machine learning model, achieves the purpose of distinguishing whether the POI to be processed exists in the database, and improves the accuracy and efficiency.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an apparatus for aggregating interest points according to an embodiment of the present invention, where the apparatus for aggregating interest points specifically includes:
a candidate module 301, configured to obtain a POI related to the input POI as a candidate POI based on the attribute of the input POI.
The determining module 302 is configured to filter the candidate POIs according to a preset rule, and determine a POI that cannot be determined to be aggregated with the input POI as a suspected POI.
The similarity module 303 is configured to input the suspected POI into a pre-trained machine learning model, so as to obtain a similarity between the suspected POI and the input POI.
The aggregation module 304 is configured to determine the corresponding suspected POI as a POI that can be aggregated with the input POI if the similarity is greater than a preset threshold.
In an embodiment of the present invention, the candidate module 301 is specifically configured to determine a candidate region based on the coordinates of the input POI, and use the POI in the candidate region as a candidate POI.
In an embodiment of the present invention, the candidate module 301 is specifically configured to, based on an attribute of the input POI, use a POI related to the input POI as a primary POI;
and adopting other attributes of the input POI to exclude POI different from the input POI from the initial selection POI to obtain a candidate POI.
In one embodiment of the invention, an attribute comprises a coordinate; other attributes include one or more of name, category, and address.
In one embodiment of the present invention, a training module 304 (not shown in fig. 3) is further included for training the machine learning model by a positive sample set and a negative sample set, the positive sample set including POIs that can be aggregated, and the negative sample set including POIs that cannot be aggregated.
Fig. 4 is a block diagram illustrating an exemplary hardware architecture of a computing device capable of implementing the method and apparatus for aggregating points of interest according to embodiments of the present invention.
As shown in fig. 4, computing device 400 includes an input device 401, an input interface 402, a central processor 403, a memory 404, an output interface 405, and an output device 406. The input interface 402, the central processing unit 403, the memory 404, and the output interface 405 are connected to each other through a bus 410, and the input device 401 and the output device 406 are connected to the bus 410 through the input interface 402 and the output interface 405, respectively, and further connected to other components of the computing device 400.
Specifically, the input device 401 receives input information from the outside and transmits the input information to the central processor 403 through the input interface 402; the central processor 403 processes the input information based on computer-executable instructions stored in the memory 404 to generate output information, stores the output information temporarily or permanently in the memory 404, and then transmits the output information to the output device 406 through the output interface 405; output device 406 outputs the output information outside of computing device 400 for use by a user.
That is, the computing device shown in fig. 4 may also be implemented to include: a memory storing computer-executable instructions; and a processor which, when executing computer executable instructions, may implement the method and apparatus of aggregating points of interest described in connection with fig. 1-3.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method of aggregating points of interest, comprising:
acquiring interest points related to input interest points as candidate interest points based on the attributes of the input interest points;
screening the candidate interest points according to a preset rule, and confirming the interest points which cannot be judged whether the candidate interest points can be aggregated with the input interest points as suspected interest points;
inputting the suspected interest point into a pre-trained machine learning model to obtain the similarity between the suspected interest point and the input interest point;
and if the similarity is greater than a preset threshold value, determining the corresponding suspected interest point as an interest point capable of being aggregated with the input interest point.
2. The method of claim 1, wherein the obtaining interest points related to the input interest points as candidate interest points based on the attributes of the input interest points comprises:
and determining a candidate region based on the coordinates of the input interest points, and taking the interest points in the candidate region as candidate interest points.
3. The method of claim 1, wherein the obtaining interest points related to the input interest points as candidate interest points based on the attributes of the input interest points comprises:
based on one attribute of the input interest point, taking the interest point related to the input interest point as an initial selection interest point;
and eliminating interest points different from the input interest points from the primarily selected interest points by adopting other attributes of the input interest points to obtain the candidate interest points.
4. The method of claim 3, wherein the one attribute comprises a coordinate;
the other attributes include one or more of a name, a category, and an address.
5. The method of claim 1, wherein before inputting the suspected interest point into a pre-trained machine learning model and obtaining the similarity between the suspected interest point and the input interest point, the method further comprises:
the machine learning model is trained by a set of positive samples including polymerizable points of interest and a set of negative samples including non-polymerizable points of interest.
6. An apparatus for aggregating points of interest, comprising:
the candidate module is used for acquiring interest points related to the input interest points as candidate interest points based on the attributes of the input interest points;
the judging module is used for screening the candidate interest points according to a preset rule and confirming the interest points which can not be judged whether to be aggregated with the input interest points as suspected interest points;
the similarity module is used for inputting the suspected interest point into a pre-trained machine learning model to obtain the similarity between the suspected interest point and the input interest point;
and the aggregation module is used for determining the corresponding suspected interest point as an interest point which can be aggregated with the input interest point if the similarity is greater than a preset threshold value.
7. The apparatus for aggregating interest points as recited in claim 6, wherein the candidate module is specifically configured to determine a candidate region based on the coordinates of the input interest points, and take the interest points in the candidate region as candidate interest points.
8. The apparatus for aggregating interest points as claimed in claim 6, wherein the candidate module is specifically configured to use an interest point related to the input interest point as an initial interest point based on an attribute of the input interest point;
and eliminating interest points different from the input interest points from the primarily selected interest points by adopting other attributes of the input interest points to obtain the candidate interest points.
9. An apparatus for aggregating points of interest,
a memory for storing a program;
a processor for executing the program stored in the memory to perform the method of aggregating points of interest according to any of claims 1-5.
10. A computer-readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811324278.9A CN111159318A (en) | 2018-11-08 | 2018-11-08 | Method, apparatus, device and medium for aggregating points of interest |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811324278.9A CN111159318A (en) | 2018-11-08 | 2018-11-08 | Method, apparatus, device and medium for aggregating points of interest |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111159318A true CN111159318A (en) | 2020-05-15 |
Family
ID=70554807
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811324278.9A Pending CN111159318A (en) | 2018-11-08 | 2018-11-08 | Method, apparatus, device and medium for aggregating points of interest |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111159318A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112860996A (en) * | 2021-02-07 | 2021-05-28 | 北京百度网讯科技有限公司 | Interest point processing method and device, electronic equipment and medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104050196A (en) * | 2013-03-15 | 2014-09-17 | 阿里巴巴集团控股有限公司 | Point of interest (POI) data redundancy detection method and device |
| CN106709606A (en) * | 2016-12-29 | 2017-05-24 | 平安科技（深圳）有限公司 | Personalized scene prediction method and apparatus |
| CN107609186A (en) * | 2017-09-30 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | Information processing method and device, terminal device and computer-readable recording medium |
-
2018
- 2018-11-08 CN CN201811324278.9A patent/CN111159318A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104050196A (en) * | 2013-03-15 | 2014-09-17 | 阿里巴巴集团控股有限公司 | Point of interest (POI) data redundancy detection method and device |
| CN106709606A (en) * | 2016-12-29 | 2017-05-24 | 平安科技（深圳）有限公司 | Personalized scene prediction method and apparatus |
| CN107609186A (en) * | 2017-09-30 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | Information processing method and device, terminal device and computer-readable recording medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112860996A (en) * | 2021-02-07 | 2021-05-28 | 北京百度网讯科技有限公司 | Interest point processing method and device, electronic equipment and medium |
| CN112860996B (en) * | 2021-02-07 | 2023-09-19 | 北京百度网讯科技有限公司 | Interest point processing method and device, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Campbell et al. | Assessing colour-dependent occupation statistics inferred from galaxy group catalogues | |
| CN106649331B (en) | Business circle identification method and equipment | |
| US10375171B2 (en) | Iterative learning for reliable sensor sourcing systems | |
| CN112712690B (en) | Vehicle electronic fence method and device and electronic equipment | |
| CN109947881B (en) | POI weight judging method and device, mobile terminal and computer readable storage medium | |
| CN110263117B (en) | Method and device for determining POI (Point of interest) data | |
| US20180340787A1 (en) | Vehicle routing guidance to an authoritative location for a point of interest | |
| CN107291713B (en) | Prompting method, terminal and server for searching keywords of interest points | |
| CA3078148A1 (en) | Search method and apparatus, and non-temporary computer-readable storage medium | |
| CN114422267B (en) | Flow detection method, device, equipment and medium | |
| WO2022134829A1 (en) | Method and apparatus for identifying same user, and computer device and storage medium | |
| CN107622061A (en) | A kind of method, apparatus and system for determining address uniqueness | |
| CN115238582A (en) | Reliability evaluation method, system, equipment and medium for knowledge graph triples | |
| CN107133689B (en) | Position marking method | |
| CN105426387B (en) | Map aggregation method based on K-means algorithm | |
| CN111159318A (en) | Method, apparatus, device and medium for aggregating points of interest | |
| CN110647602A (en) | Method and system for determining corresponding interest points based on longitude and latitude of positioning points | |
| CN113032514B (en) | Method and device for processing point of interest data | |
| CN116756616A (en) | Data processing method, device, computer readable medium and electronic equipment | |
| CN115774854A (en) | Text classification method and device, electronic equipment and storage medium | |
| CN103218406B (en) | The processing method and equipment of the address information of point of interest | |
| CN108133234B (en) | Sparse subset selection algorithm-based community detection method, device and equipment | |
| CN114341894A (en) | Hyper-parameter recommendation method for machine learning method | |
| CN115348190A (en) | Internet of things equipment detection method, system and equipment | |
| CN113076451B (en) | Abnormal behavior identification and risk model library establishment method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |